Study of intrusion detection system based on improved BP neural networks
Xiaoyan Yang, Kun Gao, Weigang Zhang · 2007
Intrusion detection is one of the core technologies in dynamic security. As an important branch of artificial intelligence, neural networks is a high efficient and parallel, non-linear dynamical system, it possesses characteristics of self-adaptive, self-learning and well expansibility. Aimed at the traditional IDS defects of high rate of false alarm and high rate of missing report, we design the method of IDS based on BP neural networks. For huge data samples, the training of the value of the weight is improved compared with the traditional back-propagation (BP) neural networks and simulation, the results show that the method is efficient.